← Back to community benchmarks

gemma-4-26B-A4B-it

M3 Ultra (80c) · 512 GB · 8bit · 2026-05-08
Performance
16k
tokens
2,125
PP tok/s
68.2
TG tok/s
7712
TTFT (ms)
26.7
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 2,125 68.2 26.7 GB current
32k 1,940 57.9 28.0 GB view
64k 1,578 43.0 29.2 GB view